python爬百度文库ppt图片

 

 

import requests

import os

from lxml import etree

 

 

# 创建目录方法

def create_file(file_path):

    if not os.path.exists(file_path):

        os.makedirs(file_path)

 

#url = 'https://wk.baidu.com/view/526297e64531b90d6c85ec3a87c24028905f8521'

#url = 'https://wenku.baidu.com/view/c618583dfc00bed5b9f3f90f76c66137ee064fbb.html?fr=income11-doc-search&_wkts_=1708924835319&wkQuery=%E6%96%B0%E5%86%A0%E8%82%BA%E7%82%8E'

#url = 'https://wenku.baidu.com/view/1fea0e827275a417866fb84ae45c3b3566ecdddd?aggId=fbb4fc21a0c7aa00b52acfc789eb172dec6399eb&fr=catalogMain_text_ernie_recall_backup_new%3Awk_recommend_main4&_wkts_=1708925067387&wkQuery=%E5%9B%BE%E7%89%87'

url = 'https://wenku.baidu.com/view/5a2b440474232f60ddccda38376baf1ffc4fe3c9.html?fr=income3-doc-search&_wkts_=1708926255145&wkQuery=%E8%AF%BE%E4%BB%B6'

#将想要的图片在百度文库地址，放在url = ''里面

resp = requests.get(url)

 

# print(resp.text)

text = resp.text

 

html = etree.HTML(text)

 

 

img_list = html.xpath('//div[@class="mod flow-ppt-mod"]/div/div/img')

 

# 计数

cnt = 1

 

# 文件保存路径

file_path = './wendang/'

create_file(file_path)

 

# 获取图片

for i in img_list:

    try:

        img_url = i.xpath('./@src')[0]

    except:

        img_url = i.xpath('./@data-src')[0]

 

    # 文件名称

    file_name = f'{file_path}page_{cnt}.jpg'

    print(file_name, img_url)

    # 下载保存图片

    resp = requests.get(img_url)

    with open(file_name, 'wb') as f:

        f.write(resp.content)

 

    cnt += 1

 

结果